On Urgency of I/O Operations

Abstract

Many high-performance parallel file systems and storage hierarchies employ multilayer storage caches in an attempt to reduce data access latencies. In current storage cache hierarchies, all data requests are treated uniformly and hit/miss characteristics are dictated only by the degree of reuse exhibited by data blocks. In reality however, different I/O operations may have different urgencies (criticalities), and in particular, some I/O operations can be delayed without having a major impact on overall application performance. Motivated by this observation, we define the concept of I/O operation urgency (criticality) and study the critical latencies of I/O operations for a set of seven high-performance applications that manipulate disk-resident data sets. We propose and experimentally evaluate three profile-based strategies for exploiting urgent I/O operations in managing storage caches. The results collected with these schemes on both two-tier and three-tier systems indicate that significant performance improvements are possible if one could exploit urgencies of different I/O operations in managing storage caches.

A Checkpoint of Research on Parallel I/O for High-Performance Computing

“…Kandemir et al [43] define the concept of requests urgency, given by how long a request can be delayed without affecting the application performance. They improve a caching mechanism by prioritizing urgent requests.…”

“…Kandemir et al [43] automatically instrument applications to delay I/O operations in order to measure the effect of this delay in final performance. Obtained information is then used to prioritize more "urgent" operations.…”